Sludge boiler tail heating surface cooperative anticorrosion control system and method based on dynamic acid dew point prediction

Abstract

The invention relates to a sludge boiler tail heating surface cooperative anticorrosion control system and method based on dynamic acid dew point prediction. A data acquisition module is used for acquiring operation data of an air preheater and an economizer; the data calculation decision module is used for calculating the acid dew point temperature in real time, determining an optimal operation data regulation and control mode and achieving a balance point of optimizing anti-corrosion control and boiler thermal efficiency; the coordinated regulation and control module carries out coordinated regulation and control on target heating temperatures and flue gas flow of an air preheater and a coal economizer; the cloud platform is used for historical operation data storage, corrosion trend analysis and fault alarm, and feeding the historical corrosion rate back to the data acquisition module. The operation data of the boiler tail heating surface are collected, the acid dew point temperature is calculated in real time in combination with a machine learning algorithm and the historical operation data of the boiler, a corrosion risk assessment system is established, real-time monitoring of a high-risk area where corrosion may occur is achieved, optimization adjustment is conducted on the boiler tail heating surface, and the corrosion risk is reduced.

Description

Technical Field

[0001] This invention relates to the field of corrosion prevention and control technology for boiler tail heating surfaces, and particularly to a collaborative corrosion prevention and control system and method for sludge boiler tail heating surfaces based on dynamic acid dew point prediction. Background Technology

[0002] With the continuous increase in sludge production, incineration has become the mainstream treatment method due to its advantages in volume reduction and resource recovery. However, the economizer and air preheater at the tail end of sludge incineration boilers are exposed to corrosive flue gas containing sulfur and chlorine for a long time, and the acid dew point corrosion problem in the low-temperature zone is prominent, resulting in a significant reduction in equipment life and efficiency.

[0003] In existing technologies, the static temperature threshold method cannot respond to dynamic changes in fuel composition due to the fixed wall temperature; the lack of acid dew point prediction leads to control lag; and the independent control of the economizer and air preheater increases energy consumption. All three factors contribute to increased corrosion risk and energy consumption. Summary of the Invention

[0004] The purpose of this invention is to provide a collaborative anti-corrosion control system and method for the tail heating surface of a sludge boiler based on dynamic acid dew point prediction, thereby solving the above-mentioned problems in the prior art.

[0005] The technical solution of the present invention to solve the above-mentioned technical problems is as follows: A collaborative corrosion prevention and control system for the tail heating surface of a sludge boiler based on dynamic acid dew point prediction includes a data acquisition module, a data calculation and decision-making module, a collaborative control module, and a cloud platform. The data acquisition module is used to collect operating data from the air preheater and economizer; The data calculation and decision-making module is electrically connected to the data acquisition module. The data calculation and decision-making module is used to calculate the acid dew point temperature in real time by combining the operating data with machine learning algorithms, and to determine the best operating data control method based on the operating data, target heating temperature, and flow rate, so as to achieve a balance between optimizing corrosion control and boiler thermal efficiency. The coordinated control module is electrically connected to the data acquisition module and the data calculation and decision-making module, respectively. The coordinated control module is used to make coordinated control of the target heating temperature of the air preheater and the economizer and the flue gas flow based on the optimal operating data control method. The cloud platform is electrically connected to the data acquisition module, the data computing and decision-making module, and the collaborative control module. The cloud platform is used for storing historical operation data, analyzing corrosion trends, and providing fault alarms. At the same time, it feeds back the historical corrosion rate to the data acquisition module.

[0006] The beneficial effects of this invention are: by collecting operating data of the boiler tail heating surface, combining machine learning algorithms and historical boiler operating data, the acid dew point temperature is calculated in real time, and a corrosion risk assessment system is established, thereby realizing real-time monitoring of high-risk areas that may be corroded, and timely optimization and adjustment of the operating conditions of the boiler tail heating surface, reducing the risk of corrosion.

[0007] Based on the above technical solution, the present invention can be further improved as follows.

[0008] Furthermore, the data acquisition module includes a flue gas composition acquisition unit, a temperature acquisition unit, an ash accumulation monitoring unit, and an operating parameter acquisition unit; The flue gas composition acquisition unit collects the concentrations of SO3 and H2O in the flue gas in real time through an ultraviolet fluorescence analyzer A1 installed in the economizer outlet flue, and collects the concentration of Cl⁻ through an ion chromatography sensor; The temperature acquisition unit acquires the temperature of the economizer outer wall through a K-type thermocouple A2 arranged on the economizer outer wall, acquires the inlet water temperature through a PT100 temperature sensor A3 installed on the economizer inlet water pipe, acquires the inlet air temperature through a duct temperature sensor C1 installed on the air preheater inlet duct, and acquires the cold end wall temperature through a corrosion-resistant thermocouple C2 arranged on the cold end wall of the air preheater. The dust accumulation monitoring unit collects dust accumulation images and thickness using an infrared thermal imager and an industrial camera D1 arranged on the heated surface area of ​​the air preheater. The operating parameter acquisition unit obtains fuel characteristics, operating parameters, and historical corrosion rate data through the boiler control system; fuel characteristics include sulfur content and ash content; operating parameters include load, oxygen content, and medium flow rate.

[0009] Furthermore, the data computing and decision-making module includes a data computing and decision-making unit and an auxiliary device decision-making unit; The data computing and decision-making unit is electrically connected to the flue gas composition acquisition unit, temperature acquisition unit, and cloud platform. It is used to combine the embedded controller to run the dynamic acid dew point prediction model and output the acid dew point temperature T. dp And through the control algorithm, based on the actual wall temperature and T dp The risk classification is determined by the temperature difference ΔT between the two, and the optimal combination of control parameters for target heating temperature and flow rate is output. At the same time, the judgment result is output to the background data of the cloud platform. The auxiliary device decision unit is electrically connected to the ash accumulation monitoring unit and the cloud platform. It is used to monitor in real time whether the ash accumulation thickness reaches the threshold and transmit a risk assessment signal to the cloud platform to determine whether to trigger the ash removal device.

[0010] Another technical solution of the present invention is as follows: A method for coordinated corrosion prevention and control of the tail-end heating surface of a sludge boiler based on dynamic acid dew point prediction, used to operate the aforementioned coordinated corrosion prevention and control system for the tail-end heating surface of a sludge boiler based on dynamic acid dew point prediction, includes the following steps: Step 1: Real-time collection of SO3 concentration, H2O concentration, and Cl concentration in flue gas. - Concentration; fuel sulfur content, fuel ash content, boiler load, flue gas oxygen content, heated surface wall temperature, medium flow rate and historical corrosion rate, sensor noise is eliminated by Kalman filtering to generate a standardized input matrix, which is then connected to the dynamic acid dew point prediction model as an input. Step 2, the dynamic acid dew point prediction model outputs T dp ; Step 3, according to T dp The air preheater and economizer are adjusted based on the current outlet temperature, wall temperature, and target heating temperature. Attached Figure Description

[0011] Figure 1 This is an architecture diagram of a collaborative corrosion prevention control system for the tail heating surface of a sludge boiler based on dynamic acid dew point prediction, according to the present invention. Figure 2 This is a schematic diagram of the structure of a collaborative anti-corrosion control system for the tail heating surface of a sludge boiler based on dynamic acid dew point prediction according to the present invention. Figure 3 This is a schematic flowchart of a collaborative corrosion prevention control method for the tail heating surface of a sludge boiler based on dynamic acid dew point prediction, according to the present invention. Detailed Implementation

[0012] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0013] Example 1 like Figures 1 to 3 As shown, a collaborative corrosion prevention control system for the tail heating surface of a sludge boiler based on dynamic acid dew point prediction includes a data acquisition module, a data calculation and decision-making module, a collaborative control module, and a cloud platform. The data acquisition module is used to collect operating data of the air preheater and economizer. In specific implementation, a corrosion electrode is also set up to detect the corrosion rate. The data calculation and decision module is electrically connected to the data acquisition module. The data calculation and decision module is used to calculate the acid dew point temperature in real time by combining the operating data with machine learning algorithms, and to determine the best operating data control method based on the operating data, target heating temperature, and flow rate, so as to achieve a balance between optimizing corrosion control and boiler thermal efficiency. In specific implementation, it is ensured that the flue gas temperature is reduced to below 120℃, while the corrosion energy consumption increase is ≤3%. The coordinated control module is electrically connected to the data acquisition module and the data calculation and decision module respectively. The coordinated control module is used to make coordinated control of the target heating temperature of the air preheater and the economizer and the flue gas flow based on the optimal operating data control method. The cloud platform is electrically connected to the data acquisition module, the data calculation and decision-making module, and the collaborative control module. The cloud platform is used for storing historical operating data, analyzing corrosion trends, and issuing fault alarms, while also feeding back the historical corrosion rate to the data acquisition module.

[0014] By collecting operating data from the boiler's tail heating surface, combining machine learning algorithms with the boiler's historical operating data, the acid dew point temperature is calculated in real time, and a corrosion risk assessment system is established. This enables real-time monitoring of high-risk areas that may experience corrosion, and timely optimization and adjustment of the boiler's tail heating surface's operating conditions to reduce the risk of corrosion.

[0015] Example 2 This embodiment is a further improvement on embodiment 1, as detailed below: The data acquisition module includes a flue gas composition acquisition unit, a temperature acquisition unit, an ash accumulation monitoring unit, and an operating parameter acquisition unit; The flue gas composition acquisition unit collects the concentrations of SO3 and H2O in the flue gas in real time through an ultraviolet fluorescence analyzer A1 installed in the economizer outlet flue, and collects the concentration of Cl⁻ through an ion chromatography sensor; The temperature acquisition unit acquires the temperature of the economizer outer wall through a K-type thermocouple A2 arranged on the economizer outer wall, acquires the inlet water temperature through a PT100 temperature sensor A3 installed in the economizer inlet water pipe, acquires the inlet air temperature through a duct temperature sensor C1 installed in the air preheater inlet duct, and acquires the cold end wall temperature through a corrosion-resistant thermocouple C2 arranged on the cold end wall of the air preheater. The ash accumulation monitoring unit collects ash accumulation images and thickness using an infrared thermal imager and an industrial camera D1 arranged in the heated surface area of ​​the air preheater. The operating parameter acquisition unit obtains fuel characteristics, operating parameters, and historical corrosion rate data through the boiler control system; the fuel characteristics include sulfur content and ash content; the operating parameters include load, oxygen content, and medium flow rate.

[0016] Example 3 This embodiment is a further improvement on embodiment 2, as detailed below: The data calculation and decision-making module includes a data calculation and decision-making unit and an auxiliary device decision-making unit; The data calculation and decision-making unit is electrically connected to the flue gas composition acquisition unit, the temperature acquisition unit, and the cloud platform, and is used to combine the embedded controller to run the dynamic acid dew point prediction model and output the acid dew point temperature T. dp And through the control algorithm, based on the actual wall temperature and T dp The risk classification is determined by the temperature difference ΔT between the two, and the optimal combination of control parameters for target heating temperature and flow rate is output. At the same time, the judgment result is output to the background data of the cloud platform. The auxiliary device decision unit is electrically connected to the ash accumulation monitoring unit and the cloud platform. It is used to monitor in real time whether the ash accumulation thickness reaches the threshold and transmit a risk assessment signal to the cloud platform to determine whether to trigger the ash removal device.

[0017] The data calculation and decision-making unit adopts a random forest model, and the input includes the concentration of SO3 in the flue gas, the concentration of H2O in the flue gas, and the concentration of Cl in the flue gas. - Concentration; 10-dimensional characteristics including fuel sulfur content, fuel ash content, boiler load, flue gas oxygen content, heated surface wall temperature, medium flow rate, and historical corrosion rate; output acid dew point temperature T. dp .

[0018] The calculation of the acid dew point temperature specifically includes: Feature variable definition: The input layer is a 10-dimensional feature vector: X: X = [x1, x2, x3, x4, x5, x6, x7, x8, x9, x 10 Where: x1: SO3 concentration in flue gas (ppm); x2: H2O concentration in flue gas (%); x3: Cl concentration in flue gas - Concentration (mg / m³); x4: Fuel sulfur content (%); x5: Fuel ash content (%); x6: Boiler load (MW); x7: Flue gas oxygen content (%); x8: Heating surface wall temperature (°C); x9: Medium flow rate (m / s); 10 Historical corrosion rate (mm / a); Random forest model construction: K sample sets are extracted from the training dataset, each sample set containing N samples, to train K decision trees; For each tree, m features (m≤10) are randomly selected from the 10-dimensional features, and the mean squared error (MSE) is used as the splitting criterion: ;in This is the actual acid dew point temperature. The node prediction value is obtained by traversing the feature thresholds to find the split point with the minimum MSE, and the decision tree is recursively constructed until the leaf node is reached. Ensemble prediction: For an input sample X, each decision tree outputs a predicted value h. k (X), the final output of the random forest is the mean of the K trees: .

[0019] The random forest model uses boiler operation data from more than 5 years and a sample set of no less than 100,000 sets for training, with a cross-validation error ≤ ±2℃; and is based on wall temperature and T dp Temperature difference ΔT=T wall -T dp Corrosion risk levels are classified, and optimal control parameters are output. Dynamic control ensures the wall temperature remains above T. dp The corrosion rate is significantly reduced.

[0020] Example 4 This embodiment is a further improvement on embodiment 3, as detailed below: The coordinated control module includes a temperature control unit, a flow control unit, a dust removal device triggering unit, and an anti-corrosion device triggering unit. The temperature control unit uses a PID algorithm to control the economizer inlet water temperature control module B1, which in turn controls the steam bypass heating system to raise the economizer inlet water temperature to T. dp +5~10℃; The electric heating module E1 at the air preheater inlet is controlled by fuzzy logic. In specific implementation, the electric heating module is 0-50kW to maintain the inlet air temperature ≥60℃. The flow control unit adjusts the flow rate of the medium in the economizer and air preheater through a frequency converter, so that the flow rate in the economizer is maintained at 1.5 to 3.0 m / s and the flow rate in the air preheater is maintained at 0.8 to 1.5 m / s. The dust removal device triggering unit is electrically connected to the auxiliary device decision unit. When the dust accumulation monitoring unit identifies that the dust accumulation thickness is ≥3mm, the dust removal device is started, triggering the ultrasonic vibrator E2 in the air preheater area to continuously remove dust for 5-10 minutes. The corrosion device triggering unit is electrically connected to the ash removal device triggering unit and starts synchronously with it. It sprays Ca(OH)2 through the Ca(OH)2 nozzle E3 located at the cold end of the air preheater at a dosage of 0.1–0.5 g / Nm³, adjusting the pH of the acidic condensate to 6.5–7.5. It supports multi-fuel co-firing scenarios such as sludge, biomass, and coal, and the algorithm is compatible with different furnace types; maintenance costs are reduced: ash removal frequency is decreased, and maintenance cycles are extended.

[0021] Example 5 This embodiment is a further improvement on embodiment 4, as detailed below: The cloud platform also supports remote parameter optimization and image recognition. It stores historical operating data and generates a solution set through a remote optimization algorithm, with the dual objectives of maximizing boiler thermal efficiency and minimizing corrosion prevention energy consumption, constrained by flue gas temperature ≤120℃ and corrosion prevention energy consumption increase ≤3%. This triggers the AI ​​image recognition module to perform thickness analysis on the images collected by the ash accumulation monitoring unit. Lowering the flue gas temperature improves boiler thermal efficiency.

[0022] The logic for classifying corrosion risk levels is as follows: Low risk: ΔT ≥ 10℃, the coordinated control module maintains the current operating state; Medium risk: 5℃ ≤ ΔT < 10℃, the coordinated control module only activates the temperature control unit and the flow control unit; High risk: ΔT < 5℃, triggering ultrasonic rapper E2 dust removal and Ca (OH)2 nozzle E3 corrosion inhibitor spraying.

[0023] Example 6 A method for coordinated corrosion prevention control of the tail-end heating surface of a sludge boiler based on dynamic acid dew point prediction is used to operate the coordinated corrosion prevention control system for the tail-end heating surface of a sludge boiler based on dynamic acid dew point prediction as described in any of Examples 1 to 5 above, and includes the following steps: Step 1: Real-time collection of SO3 concentration, H2O concentration, and Cl concentration in flue gas. - Concentration; fuel sulfur content, fuel ash content, boiler load, flue gas oxygen content, heated surface wall temperature, medium flow rate and historical corrosion rate, sensor noise is eliminated by Kalman filtering to generate a standardized input matrix, which is then connected to the dynamic acid dew point prediction model as an input. Step 2, the dynamic acid dew point prediction model outputs T dp ; Step 3, according to T dp The air preheater and economizer are adjusted based on the current outlet temperature, wall temperature, and target heating temperature.

[0024] In practical implementation, when 5℃≤ΔT<10℃, the temperature control unit is activated. The economizer inlet water temperature control module B1 activates the steam bypass heating system, adjusting the steam flow rate using a PID algorithm to raise the water temperature to Tdp+5~10℃, until ΔT≥10℃, at which point the equipment is in a low-risk phase. An electric heating module heats the air at the air preheater inlet, maintaining an air temperature ≥60℃ based on fuzzy logic control (gas-fired supplementary combustion is activated under extreme conditions). Based on ultrasonic flow meter monitoring of flue gas flow rate and corrosion risk level, the circulating water pump speed is adjusted via a frequency converter to maintain the economizer flow rate range at 1.5~3.0m / s and the air preheater flow rate at 0.8~1.5m / s.

[0025] When ΔT < 5℃, the ultrasonic vibrator E2 in the air preheater area and the Ca(OH)2 nozzle E3 located at the cold end of the air preheater are triggered. The dust accumulation monitoring and cleaning triggering device uses AI image recognition technology to analyze data from infrared thermal imagers and industrial cameras to identify the dust accumulation thickness. When the dust accumulation thickness is ≥ 3mm, the ultrasonic vibrator E2 is triggered to vibrate at a high frequency of 20-40kHz for 5-10 minutes, with a cleaning efficiency ≥ 90%. The Ca(OH)2 nozzle E3 sprays Ca(OH)2 at a dosage of 0.1-0.5g / Nm³ at the cold end of the air preheater through a pneumatic delivery nozzle to neutralize the acidic condensate, thereby adjusting the pH to 6.5-7.5.

[0026] In the acid dew point prediction model, boiler thermal efficiency (η) and corrosion prevention energy consumption (E) are used as dual objective functions to establish a solution set. Constraints include flue gas temperature ≤120℃ and corrosion prevention energy consumption increase ≤3%, and the final output is the optimal combination of control parameters (such as steam heating amount, electric heating power, and flow rate).

[0027] Operation control system 1. The proportion of sludge co-firing increased from 30% to 50%, and the SO3 concentration in the flue gas increased from 15 ppm to 25 ppm; 2. Dynamic acid dew point prediction model predicts T dp The temperature rose from 95℃ to 108℃; 3. The system automatically starts steam heating, raising the economizer inlet water temperature from 105℃ to 115℃, and increases the electric heating power of the air preheater to make the inlet air temperature reach 65℃; 4. Image recognition showed that the dust accumulation thickness on the air preheater exceeded the limit, triggering the E2 ultrasonic rapper for dust removal; 5. Real-time monitoring shows that the wall temperature is stable at ΔT≥10℃, and the corrosion risk is reduced to "low risk".

[0028] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A sludge boiler tail heating surface synergistic corrosion control system based on dynamic acid dew point prediction, characterized in that, The system comprises a data acquisition module, a data calculation and decision module, a collaborative control module and a cloud platform. The data acquisition module is used for collecting operation data of the air preheater and the coal economizer. The data calculation and decision module is electrically connected with the data acquisition module, and is used for calculating an acid dew point temperature in real time by combining the operation data with a machine learning algorithm, and determining an optimal operation data control mode according to the operation data, a target heating temperature and a flow rate, so as to achieve a balance point of optimized corrosion control and boiler thermal efficiency. The collaborative control module is electrically connected with the data acquisition module and the data calculation and decision module, and is used for making collaborative control of the target heating temperature of the air preheater and the coal economizer and the flow rate of flue gas according to the optimal operation data control mode. The cloud platform is electrically connected with the data acquisition module, the data calculation and decision module and the collaborative control module, and is used for storing historical operation data, analyzing corrosion trends and alarming faults, and feeding back a historical corrosion rate to the data acquisition module.

2. The sludge boiler tail heating surface synergistic corrosion control system based on dynamic acid dew point prediction according to claim 1, characterized in that, The data acquisition module comprises a flue gas component acquisition unit, a temperature acquisition unit, a soot deposition monitoring unit and an operation parameter acquisition unit. The flue gas component acquisition unit acquires the concentrations of SO3 and H2O in flue gas in real time by using an ultraviolet fluorescence analyzer arranged at an outlet flue of the coal economizer, and acquires the concentration of Cl- by using an ion chromatography sensor. The temperature acquisition unit acquires the temperature of the outer wall of the coal economizer by using a K-type thermocouple arranged on the outer wall of the coal economizer, acquires the inlet water temperature by using a PT100 temperature sensor arranged on an inlet water pipe of the coal economizer, acquires the inlet air temperature by using a flue temperature sensor arranged on an inlet flue of the air preheater, and acquires the cold end wall temperature by using an anti-corrosion thermocouple arranged on the cold end wall of the air preheater. The soot deposition monitoring unit acquires soot deposition images and thicknesses by using an infrared thermal imager and an industrial camera arranged in the heating surface area of the air preheater. The operation parameter acquisition unit acquires fuel characteristics, operation parameters and historical corrosion rate data by using a boiler control system; the fuel characteristics include sulfur content and ash content; the operation parameters include load, oxygen content and medium flow rate.

3. The sludge boiler tail heating surface synergic corrosion control system based on dynamic acid dew point prediction according to claim 2, characterized in that, The data calculation and decision module comprises a data calculation and decision unit and an auxiliary device decision unit. The data calculation decision unit is electrically connected with the flue gas component collection unit and the temperature collection unit, and is used for running a dynamic acid dew point prediction model to output an acid dew point temperature T dp by combining the embedded controller, and making risk classification according to a temperature difference ΔT between an actual wall temperature and T dp , outputting a target heating temperature and a flow optimal control parameter combination, and outputting the judgment result to the background data of the cloud platform. The auxiliary device decision unit is electrically connected with the soot deposition monitoring unit and the cloud platform, and is used for monitoring whether the soot deposition thickness reaches a threshold value in real time, and transmitting a risk assessment signal to the cloud platform to determine whether to trigger a soot cleaning device.

4. The sludge boiler tail heating surface synergistic corrosion control system based on dynamic acid dew point prediction according to claim 3, characterized in that, The dynamic acid dew point prediction model adopts a random forest model, and the input includes the SO3 concentration in flue gas, the H2O concentration in flue gas, the Cl - concentration in flue gas; 10-dimensional features of fuel sulfur content, fuel ash content, boiler load, flue gas oxygen content, heating surface wall temperature, medium flow rate, and historical corrosion rate Output acid dew point temperature T dp .

5. The sludge boiler tail heating surface synergic corrosion control system based on dynamic acid dew point prediction according to claim 4, characterized in that, The calculation of the acid dew point temperature specifically comprises: Feature variable definition: the input layer is a 10-dimensional feature vector: X: X = [x1, x2, x3, x4, x5, x6, x7, x8, x9, x 10 ], wherein: x1: SO3 concentration in flue gas (ppm); x2: H2O concentration in flue gas (%); x3: Cl- concentration in flue gas (mg / m³); x4: fuel sulfur content (%); x5: fuel ash content (%); x6: boiler load (MW); x7: flue gas oxygen content (%); x8: heating surface wall temperature (℃); x9: medium flow rate (m / s); x 10 : historical corrosion rate (mm / a); Random forest model construction: K sample sets are extracted from a training data set, each sample set containing N samples, for training K decision trees; For each tree, m features are randomly selected from the 10-dimensional feature set, and the mean square error (MSE) is used as the splitting criterion: ; wherein is the true acid dew point temperature, is the node prediction value, and the splitting point with the minimum MSE is found by traversing the feature threshold value, and the decision tree is recursively constructed until the leaf node. Integrated prediction: for each input sample X, each decision tree outputs a prediction value h k (X), and the random forest outputs the average of the K trees: .

6. The sludge boiler tail heating surface synergic corrosion control system based on dynamic acid dew point prediction according to claim 5, characterized in that, The random forest model uses boiler operation data from more than 5 years and a sample set of no less than 100,000 sets for training, with a cross-validation error ≤ ±2℃; and is based on wall temperature and T dp Temperature difference ΔT=T wall -T dp Classify corrosion risk levels and output optimal control parameters.

7. The sludge boiler tail heating surface synergic corrosion control system based on dynamic acid dew point prediction according to claim 6, characterized in that, The collaborative control module comprises a temperature control unit, a flow control unit, a soot cleaning device triggering unit and an anti-corrosion device triggering unit. The temperature regulation unit controls the water temperature control module at the inlet of the coal economizer by a PID algorithm to control the steam bypass heating system, so that the water temperature at the inlet of the coal economizer is raised to T dp +5~10℃; the electric heating module at the inlet of the air preheater is controlled by fuzzy logic to maintain the inlet air temperature ≥ 60℃; The flow control unit adjusts the medium flow rates in the coal economizer and the air preheater by using a frequency converter, so that the flow rate in the coal economizer is maintained at 1.5-3.0 m / s, and the flow rate in the air preheater is maintained at 0.8-1.5 m / s. The ash removal device trigger unit is electrically connected with the auxiliary device decision unit, when the ash deposition monitoring unit identifies that the ash deposition thickness is greater than or equal to 3 mm, the ash removal device is started, the ultrasonic vibrator in the air preheater area is triggered, and ash removal is continued for 5-10 minutes; The corrosion device trigger unit is electrically connected with the ash removal device trigger unit and is started synchronously with the ash removal device trigger unit, Ca (OH)2 nozzles arranged at the cold end of the air preheater are sprayed at a dose of 0.1-0.5 g / Nm3, and the acidic condensate pH is adjusted to 6.5-7.

5.

8. The sludge boiler tail heating surface synergic corrosion control system based on dynamic acid dew point prediction according to claim 7, characterized in that, The cloud platform also supports remote parameter optimization and image recognition; the cloud platform stores historical operation data, generates a solution set with the dual objectives of maximizing the boiler thermal efficiency and minimizing the corrosion energy consumption, the constraint condition being that the flue gas temperature is less than or equal to 120 DEG C and the corrosion energy consumption increment is less than or equal to 3%, and triggers the AI image recognition module to analyze the thickness of the images collected by the ash deposition monitoring unit.

9. The tail heating surface synergistic corrosion control system of the sludge boiler based on dynamic acid dew point prediction according to claim 6, characterized in that, The corrosion risk level division logic is as follows: Low risk: ΔT is greater than or equal to 10 DEG C, and the cooperative regulation module maintains the current operation state; Medium risk: 5 DEG C is less than or equal to ΔT and is less than 10 DEG C, and the cooperative regulation module only starts the temperature regulation unit and the flow regulation unit; High risk: ΔT is less than 5 DEG C, and the ultrasonic vibrator ash removal and Ca (OH)2 nozzle corrosion inhibitor spraying are triggered.

10. A method for the synergic corrosion control of tail heating surfaces of a sludge boiler based on the dynamic prediction of the acid dew point, for operating the synergic corrosion control system of tail heating surfaces of a sludge boiler based on the dynamic prediction of the acid dew point according to any one of claims 1 to 9, characterized by, The method comprises the following steps: Step 1, real-time acquisition of SO3 concentration in flue gas, H2O concentration in flue gas, Cl - concentration in flue gas; fuel sulfur content, fuel ash content, boiler load, flue gas oxygen content, heating surface wall temperature, medium flow rate and historical corrosion rate, eliminate sensor noise by Kalman filtering to generate a standardized input matrix as an input end connected to a dynamic acid dew point prediction model; Step 2, dynamic acid dew point prediction model output T dp ; Step 3, according to T dp The air preheater and the economizer are regulated based on the current outlet temperature, the wall temperature, and the target heating temperature.

Images